Model comparison
DeepSeek LLM 67B vs Magistral Medium
Magistral Medium is the stronger model overall, scoring 35.2 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Magistral Medium in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 7.0.
Side by side
| DeepSeek LLM 67B | Magistral Medium | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 24.9 | 35.2 |
| Released | 2023-11-29 | 2025-03-17 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $5 |
| Results tracked | 15 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
DeepSeek LLM 67B: 31.9 (#278), Magistral Medium: 39.1 (#161)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Coding | 1096 | 1319 |
| SciCode | — | 39.2% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), Magistral Medium: 8.6 (#348)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Magistral Medium leads
DeepSeek LLM 67B: 8.7 (#324), Magistral Medium: 35.1 (#189)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Math | 1108 | 1250 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Magistral Medium leads
DeepSeek LLM 67B: 7.0 (#313), Magistral Medium: 33.5 (#202)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1223 |
Multilingual Magistral Medium leads
DeepSeek LLM 67B: 29.4 (#267), Magistral Medium: 39.6 (#224)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1073 | 1232 |
| LMArena Chinese | 1132 | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |
Instruction Following Magistral Medium leads
DeepSeek LLM 67B: 55.4 (#277), Magistral Medium: 66.0 (#211)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1079 | 1254 |
Long Context Magistral Medium leads
DeepSeek LLM 67B: 33.1 (#265), Magistral Medium: 39.3 (#183)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1092 | 1295 |
Writing & Preference Magistral Medium leads
DeepSeek LLM 67B: 31.6 (#282), Magistral Medium: 46.3 (#219)
| Benchmark | DeepSeek LLM 67B | Magistral Medium |
|---|---|---|
| LMArena Text | 1105 | 1255 |
| LMArena Creative Writing | 1067 | 1245 |
| LMArena Multi-Turn | 1082 | 1275 |
Frequently asked questions
Is DeepSeek LLM 67B better than Magistral Medium?
Magistral Medium is the stronger model overall, scoring 35.2 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Magistral Medium better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Magistral Medium share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Magistral Medium has 22.